Agent-based Automated Claim Matching with Instruction-following LLMs

TL;DR

This paper introduces an agent-based method utilizing instruction-following LLMs for automated claim matching, improving performance with prompt generation and multi-LLM strategies, while reducing computational costs.

Contribution

It presents a novel two-step pipeline leveraging LLMs for prompt creation and claim matching, demonstrating efficiency and performance gains over existing methods.

Findings

LLM-generated prompts outperform human-crafted prompts.

Smaller LLMs can match larger ones in prompt generation.

Using different LLMs for each pipeline step enhances effectiveness.

Abstract

We present a novel agent-based approach for the automated claim matching task with instruction-following LLMs. We propose a two-step pipeline that first generates prompts with LLMs, to then perform claim matching as a binary classification task with LLMs. We demonstrate that LLM-generated prompts can outperform SOTA with human-generated prompts, and that smaller LLMs can do as well as larger ones in the generation process, allowing to save computational resources. We also demonstrate the effectiveness of using different LLMs for each step of the pipeline, i.e. using an LLM for prompt generation, and another for claim matching. Our investigation into the prompt generation process in turn reveals insights into the LLMs' understanding of claim matching.